Effective micro-expression recognition using relaxed K-SVD algorithm

Abstract

Regarded as its subtlety, micro-expression is a challenging research problem. In the paper, we propose a relax K-SVD classifier (RK-SVD) for micro-expression recognition. RK-SVD minimizes the variance of sparse coefficients to address the similarity of same classes and the distinctiveness of different classes in sparse coefficients. In addition, reconstruction error and classification error are also considered. The optimization is implemented by the K-SVD algorithm and stochastic gradient descent algorithm. Finally a single overcomplete dictionary and an optimal linear classifier are learned simultaneously. We show that RK-SVD can effectively recognize micro-expression under three spontaneous micro-expression datasets including SMIC, CASME, and CASME II.